Declarative Grafana / Prometheus / Loki / Tempo observability stack

Deploys the whole stack into the observability namespace of the local
cluster with Kustomize alone — no helm install, no dashboard created by
hand in the UI. The Makefile carries every command: deploy, dashboards,
diagnostics, PVC flush, teardown.

Dashboards are files, never UI objects. Each carries a stable uid, which
is what keeps URLs, cross-links and alerts alive across redeployments, and
references datasources by stable uid rather than by name. The dashboard
ConfigMap is generated without a name-suffix hash so applying it updates
it in place and Grafana reloads without a restart, while the provisioning
ConfigMaps keep their hash precisely so that a change there does force one.

Prometheus scrapes the kubelet /metrics/resource endpoint rather than
/metrics/cadvisor: on this cluster cadvisor exposes machine_* series only
and no container_* at all, which would leave every CPU and memory panel
empty.

Alloy ships every pod's logs to Loki through the Kubernetes API, so no
/var/log mount is needed. Tempo's metrics_generator feeds span metrics and
the service graph back into Prometheus, and the datasources are wired so a
log line's trace_id opens the matching trace.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
Stéphane Tailland
2026-08-25 07:27:38 +02:00
commit 3937b4f366
42 changed files with 7597 additions and 0 deletions
+177
View File
@@ -0,0 +1,177 @@
global:
scrape_interval: 30s
evaluation_interval: 30s
external_labels:
cluster: orbstack
source: prometheus
scrape_configs:
# --- Control plane -------------------------------------------------------
- job_name: kubernetes-apiservers
kubernetes_sd_configs:
- role: endpoints
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
insecure_skip_verify: true
authorization:
credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token
relabel_configs:
- source_labels:
[__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
action: keep
regex: default;kubernetes;https
# --- Kubelet -------------------------------------------------------------
- job_name: kubernetes-nodes
kubernetes_sd_configs:
- role: node
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
insecure_skip_verify: true
authorization:
credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
- target_label: __address__
replacement: kubernetes.default.svc:443
- source_labels: [__meta_kubernetes_node_name]
regex: (.+)
target_label: __metrics_path__
replacement: /api/v1/nodes/$1/proxy/metrics
# --- Container resource metrics -----------------------------------------
# /metrics/resource and NOT /metrics/cadvisor: on this cluster (OrbStack) the
# kubelet's cadvisor endpoint only exposes `machine_*` series and no
# `container_*` at all. /metrics/resource -- the source metrics-server reads --
# provides container_cpu_usage_seconds_total and
# container_memory_working_set_bytes with namespace/pod/container labels.
- job_name: kubernetes-kubelet-resource
kubernetes_sd_configs:
- role: node
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
insecure_skip_verify: true
authorization:
credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
- target_label: __address__
replacement: kubernetes.default.svc:443
- source_labels: [__meta_kubernetes_node_name]
regex: (.+)
target_label: __metrics_path__
replacement: /api/v1/nodes/$1/proxy/metrics/resource
- source_labels: [__meta_kubernetes_node_name]
target_label: node
# --- Services annotated with prometheus.io/scrape -----------------------
- job_name: kubernetes-service-endpoints
kubernetes_sd_configs:
- role: endpoints
relabel_configs:
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
action: keep
regex: "true"
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
action: replace
target_label: __scheme__
regex: (https?)
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
action: replace
target_label: __metrics_path__
regex: (.+)
- source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
action: replace
target_label: __address__
regex: ([^:]+)(?::\d+)?;(\d+)
replacement: $1:$2
- action: labelmap
regex: __meta_kubernetes_service_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
target_label: namespace
- source_labels: [__meta_kubernetes_service_name]
target_label: service
- source_labels: [__meta_kubernetes_pod_name]
target_label: pod
- source_labels: [__meta_kubernetes_pod_node_name]
target_label: node
# --- Pods annotated with prometheus.io/scrape ---------------------------
- job_name: kubernetes-pods
kubernetes_sd_configs:
- role: pod
relabel_configs:
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
action: keep
regex: "true"
# A pod yields one target per container: without this filter the init
# containers duplicate the real target.
- source_labels: [__meta_kubernetes_pod_container_init]
action: drop
regex: "true"
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scheme]
action: replace
target_label: __scheme__
regex: (https?)
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
action: replace
target_label: __metrics_path__
regex: (.+)
- source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
action: replace
target_label: __address__
regex: ([^:]+)(?::\d+)?;(\d+)
replacement: $1:$2
- action: labelmap
regex: __meta_kubernetes_pod_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
target_label: namespace
- source_labels: [__meta_kubernetes_pod_name]
target_label: pod
- source_labels: [__meta_kubernetes_pod_node_name]
target_label: node
- source_labels: [__meta_kubernetes_pod_container_name]
target_label: container
- source_labels: [__meta_kubernetes_pod_phase]
action: drop
regex: (Succeeded|Failed|Pending)
# --- LibreChat: /metrics behind a Bearer token --------------------------
# Annotation-based discovery cannot carry credentials, so LibreChat gets its
# own job. The token comes from the `librechat-metrics` secret mounted into
# the Prometheus pod and must match METRICS_SECRET on the LibreChat side.
- job_name: librechat
kubernetes_sd_configs:
- role: pod
namespaces:
names: [librechat]
authorization:
type: Bearer
credentials_file: /etc/prometheus/secrets/librechat/token
relabel_configs:
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape_with_auth]
action: keep
regex: "true"
# A pod yields one target per container: without this filter the init
# containers duplicate the real target.
- source_labels: [__meta_kubernetes_pod_container_init]
action: drop
regex: "true"
- source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
action: replace
target_label: __address__
regex: ([^:]+)(?::\d+)?;(\d+)
replacement: $1:$2
- source_labels: [__meta_kubernetes_namespace]
target_label: namespace
- source_labels: [__meta_kubernetes_pod_name]
target_label: pod
- source_labels: [__meta_kubernetes_pod_container_name]
target_label: container
- target_label: service
replacement: librechat